Revision Topic 13: Statistics 1

Averages
There are three common types of average: the mean, median and mode.
The mode (or modal value) is the data value (or values) that occurs the most often.
The median is the middle value, once all the data has been written in order of size. If there are n
values in a list, the median is in position

n 1
.
2

The mean is found by adding all the data values together and dividing by the total frequency.
When to use each type of average
The mode is particularly useful for non-numerical data (such as eye colour or make of car) it is
the only average that can be found for data that is not numerical. It is also frequently used for
sizes of clothes.
The mean is used when the data are reasonably symmetrical with no anomalous (or outlying
values). It is the most commonly used average.
The median is useful when that data are skewed or when there are anomalous values in the data.
Grade C example for the mean
A class took a test. The mean mark for the 20 boys in the class was 17.4. The mean mark for the 10
girls in the class was 13.8.
(a)
Calculate the mean mark for the whole class.
5 pupils in another class took the test. Their marks, written in order, were 1, 2, 3, 4 and x.
The mean of these 5 marks is twice the median of these marks.
(b)
Calculate the value of x.
Solution
(a) To find the mean mark for the whole class we divide the total of all the classs marks by
30 (since 30 is the number of pupils in the class).
total

The total of the boys marks is 17.4 20 = 348 (as mean = frequency
so total = mean total frequency)
The total of the girls marks is 13.8 10 = 138.
Therefore the total for the whole class is 348 + 138 = 486
So the mean mark for the class is 486 30 = 16.2.
(b) As the marks are written in order, the median mark is 3 (i.e. the middle mark).
So the mean of all 5 marks must be 6
(as it is twice the median).
Therefore the total of all 5 marks must be 6 5 = 30.
The sum of the first four numbers is 1 + 2 + 3 + 4 = 10.
So, the value of x must be 30 10 = 20.
Examination question 1:
27 boys and 34 girls took the same test.
The mean mark of the boys was 76. The mean mark of the girls was 82.
Calculate the mean mark of all these students. Give your answer correct to 1 decimal place.

Dr Duncombe

February 2004

Examination question 2 (non-calculator paper):

A shop employs 8 men and 2 women.
The mean weekly wage of the 10 employees is 396. The mean weekly wage of the 8 men is 400.
Calculate the mean weekly wage of the 2 women.

Finding the mean, median and mode from a table

Example 1: Frequency table
The table shows the boot sizes of players on a rugby team.
Boot size
8
9
10
11

Find

a) the mode

b) the median,

Frequency
3
5
6
1

c) the mean boot size.

Solution
a)
The mode is the boot size that occurs most often. The modal size is therefore size 10.
b)
The total number of rugby players is 15 (add up the frequency column).
The median is the value in position

c)

n 1 15 1

8.
2
2

The first three players have size 8; the next 5 have size 9. Therefore the 8th player has
size 9 boots.
To find the mean, we add an extra column to the table:
Boot size, x
8
9
10
11
TOTAL

Frequency, f
3
5
6
1
15

Boot size freq, x f

8 3 = 24
9 5 = 45
10 6 = 60
11 1 = 11
140

This is the
total of the
boot sizes of
all 15 players
You find the mean by dividing the total of the x f column divided by the total of the
frequency column:
Mean = 140 15 = 9.33
(to 3 sf).

Examination question
20 students took part in a competition. The frequency table shows information about the points
they scored.
Points scored
1
2
3

Frequency
9
4
7

Work out the mean number of points scored by the 20 students.

Dr Duncombe

February 2004

Example 2: Grouped frequency table

The table shows the masses of a group of children.
(a) Calculate an estimate of the mean mass.
(b) Find the modal interval.
(c) Find the interval that contains the median.

Mass (kg)
40 50
50 60
60 70
70 - 80

Frequency
3
10
6
12

Note: We cannot find the exact value of the mean from a grouped frequency table as we do not
know the actual values of the data are not known. We can estimate the mean if we assume that all
the values in each class are equal to the mid-point of that class.
The middle of
(a) We add 2 further columns to the table:
the interval 4050 is 45
Mass (kg)
Frequency, f
Midpoint, x
xf
40 50
3
45
345 = 135
50 60
10
55
550
60 70
6
65
390
70 - 80
12
75
900
Total
31
1975
The mean is the total of the x f column divided by the total of the frequency column:
1975 31 = 63.7 kg (to 1 dp)
Note: We should check that our mean mass is sensible (i.e. lies within the range of the data).
(b) The interval that occurs the most often is 70-80 kg. This is the modal interval.
(c) The median is in position

n 1 31 1

16 .
2
2

There are 13 children with weights below 60 kg and 19 children below 70 kg. Therefore the
median weight lies within the 60 70 kg interval.
Examination question:
75 boys took part in a darts competition. Each boy threw darts until he hit the centre of the
dartboard. The numbers of darts thrown by the boys are grouped in this frequency table.
Number of darts
thrown
1 to 5
6 to 10
11 to 15
16 to 20
21 to 25
26 to 30

Frequency
10
17
12
4
12
20

(a) Work out the class interval which contains the median.

(b) Work out an estimate for the mean number of darts thrown by each boy.

Dr Duncombe

February 2004

Cumulative frequency tables and curves

Cumulative frequency curves can be used to find the median for grouped tables. They can also be
used to find the interquartile range.
The interquartile range is a measure of spread. It tells you how variable the data are. The
interquartile range (IQR) is found using the formula
IQR = upper quartile lower quartile
The interquartile range is a better measure of spread than the range because it is less effected by
extreme values in the data.
This interval is
Example:
short for 50 60
A secretary weighed a sample of letters to be posted.
g
Mass (g)
Number of students

20 2

30 4

40 12

50 7

60 8

70 17

80 90
3

Draw a cumulative frequency graph for the data

Use your graph to find the median weight of a letter and the interquartile range of the weights.
Solution:
We first need to work out the cumulative frequencies these are a running total of the frequencies.
Mass (g)
20 are
30 18
There
30

letters 40
so far
40 50
50 60
There
60 70are
54
70 letters
80
below
80 90

Frequency
2
4
12
7
8
17
4

Cumulative frequency
2
6
18
25
33
50
54

90g
We plot the cumulative frequency graph by plotting the cumulative frequencies on the vertical axis
and the masses on the horizontal axis. It is important that the cumulative frequencies are plotted
above the endpoint of each interval. So we plot the points (30, 2), (40, 6), (50, 18), , (90, 54).
As no letter weighed less than 20g, we can also plot the point (20, 0).

The
median
is about
62g

L.Q. is
about 47g

Dr Duncombe

U.Q. is
about
75g
February 2004

The total number of letters examined was 54. The median will be approximately the 54 2 = 27th
letter. We draw a line across from 27 on the vertical axis and then find the median on the horizontal
axis. We see that the median is about 62g.
The lower quartile will be the

1
54 13.5th value. From the horizontal scale we find that the
4

lower quartile is about 47g.

The upper quartile is the

3
54 40.5th value. This is about 75g.
4

Therefore the interquartile range is

U.Q L.Q. = 75 47 = 28g.

Note: We can represent the data in the above example as a box-and-whisker plot. A box plot is a
simple diagram that is based on 5 measurements:
The lowest value
The lower quartile
The median
The upper quartile
The largest value.
In the example above we dont know the exact values of the lightest and heaviest letters. However
we do know that no letter weighed less than 20g and no letter weighed more than 90g. So we take
the lowest and largest values as 20g and 90g respectively.
The box plot we get is as follows:
median
Upper quartile
Lower quartile

20

30

Largest value

40

50

60

70

80

90

Mass (g)

Smallest value

Examination question
At a supermarket, members of staff recorded the lengths of time that 80 customers had to wait in the
queues at the checkouts.
The waiting times are grouped in the frequency table below.
Waiting time (t seconds)
0 < t 50
50 < t 100
100 < t 150
150 < t 200
200 < t 250
250 < t 300

Frequency
4
7
10
16
30
13

(a) Complete the cumulative frequency table below.

Waiting time (t seconds)
0 < t 50
50 < t 100
100 < t 150
150 < t 200
200 < t 250
250 < t 300

Dr Duncombe

February 2004

Cumulative frequency

(b) On the grid below, draw a cumulative frequency graph for this data.

(c) Use your graph to work out an estimate for

the median waiting time,

the number of these customers who had to wait more than three minutes.

Dr Duncombe

February 2004

Examination Question
The grouped frequency table gives information about the weekly rainfall (d) in millimetres at
Heathrow airport in 1995.
Weekly rainfall
(d) in mm
0 d < 10
10 d < 20
20 d < 30
30 d < 40
40 d < 50
50 d < 60

Number of
weeks
20
18
6
4
2
2

a) Copy the table and complete it to calculate an estimate for the mean weekly rainfall.
b) Write down the probability that the rainfall in any week in 1995, chosen at random, was
greater than or equal to 20mm and less than 40mm.
c) Copy and complete this cumulative frequency table for the data.
Weekly rainfall
Cumulative
(d) in mm
frequency
0 d < 10
10 d < 20
20 d < 30
30 d < 40
40 d < 50
50 d < 60
d)
Draw a cumulative frequency graph to show the data.
e)
Use your cumulative frequency graph to estimate the median weekly rainfall and the
interquartile range.

Dr Duncombe

February 2004